首页|A Generative Adversarial Network with an Attention Spatiotemporal Mechanism for Tropical Cyclone Forecasts

A Generative Adversarial Network with an Attention Spatiotemporal Mechanism for Tropical Cyclone Forecasts

扫码查看
原文链接
  • 万方数据
  • 维普
Tropical cyclones(TCs)are complex and powerful weather systems,and accurately forecasting their path,structure,and intensity remains a critical focus and challenge in meteorological research.In this paper,we propose an Attention Spatio-Temporal predictive Generative Adversarial Network(AST-GAN)model for predicting the temporal and spatial distribution of TCs.The model forecasts the spatial distribution of TC wind speeds for the next 15 hours at 3-hour intervals,emphasizing the cyclone's center,high wind-speed areas,and its asymmetric structure.To effectively capture spatiotemporal feature transfer at different time steps,we employ a channel attention mechanism for feature selection,enhancing model performance and reducing parameter redundancy.We utilized High-Resolution Weather Research and Forecasting(HWRF)data to train our model,allowing it to assimilate a wide range of TC motion patterns.The model is versatile and can be applied to various complex scenarios,such as multiple TCs moving simultaneously or TCs approaching landfall.Our proposed model demonstrates superior forecasting performance,achieving a root-mean-square error(RMSE)of 0.71 m s-1 for overall wind speed and 2.74 m s-1 for maximum wind speed when benchmarked against ground truth data from HWRF.Furthermore,the model underwent optimization and independent testing using ERA5 reanalysis data,showcasing its stability and scalability.After fine-tuning on the ERA5 dataset,the model achieved an RMSE of 1.33 m s-1 for wind speed and 1.75 m s-1 for maximum wind speed.The AST-GAN model outperforms other state-of-the-art models in RMSE on both the HWRF and ERA5 datasets,maintaining its superior performance and demonstrating its effectiveness for spatiotemporal prediction of TCs.

tropical cyclonesspatiotemporal predictiongenerative adversarial networkattention spatiotemporal mechanismdeep learning

Xiaohui LI、Xinhai HAN、Jingsong YANG、Jiuke WANG、Guoqi HAN、Jun DING、Hui SHEN、Jun YAN

展开 >

Satellite Ocean Environment Dynamics,Second Institute of Oceanography,Ministry of Natural Resources,Hangzhou 310012,China

School of Oceanography,Shanghai Jiao Tong University,Shanghai 200240,China

Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai),Zhuhai 519082,China

School of Artificial Intelligence,Sun Yat-sen University,Zhuhai 519082,China

Fisheries and Oceans Canada,Institute of Ocean Sciences,Sidney V8L 4B2,Canada

Zhejiang Marine Monitoring and Forecasting Center,Hangzhou 310007,China

展开 >

2025

10.1007/s00376-024-3243-6

大气科学进展(英文版)
中国科学院大气物理研究所

大气科学进展(英文版)

影响因子：0.741
ISSN：0256-1530
年,卷(期)：2025.42(1)